Local model network identification for online engine modelling

In this paper an evolving local model network (LMN) which is especially suited for engine modelling is presented and discussed. The incremental construction of the model tree allows to gradually increase the model complexity while a proper initialisation of new model parameters is easily possible when the LMN is extended. Especially in dynamic system identification the computational speed is an important requirement for online training. Therefore, a new evolving optimisation algorithm for the online training of the LMN is proposed which allows for a recursive computation of the model parameters. while the local interpretability of the consequent parameters is conserved. The decision when to grow the tree is based on an effective statistical criterion. The proposed concepts are validated by means of an illustrative example and by real dynamic measurement data from a state-of-the-art 4-cylinder EURO5 diesel engine.